Search papers, labs, and topics across Lattice.
6
0
3
PNEC-Mamba achieves superior classification performance by explicitly calibrating pixel-level evidence reliability, revealing the critical role of evidence separation in hyperspectral image analysis.
Vision-language models struggle with remote-sensing videos, but a new framework boosts their accuracy by over 9% in critical tasks.
Preserving full-band spectral information in hyperspectral image classification can significantly boost model performance while keeping parameter tuning minimal.
Forget satellite-specific hacks: FoundPS achieves state-of-the-art pansharpening performance with a single model robust to diverse sensors and scenes.
Forget training separate models for every remote sensing modality pair: Any2Any learns a single latent space for unified translation, even generalizing to unseen modality combinations.
You can cut MLLM hallucinations in remote sensing tasks without any training by cleverly exploiting the model's own attention mechanisms to focus on relevant image regions.
